Browse DORAS
Browse Theses
Search
Latest Additions
Creative Commons License
Except where otherwise noted, content on this site is licensed for use under a:

MATREX: DCU machine translation system for IWSLT 2006

Stroppa, Nicolas and Way, Andy (2006) MATREX: DCU machine translation system for IWSLT 2006. In: IWSLT 2006 - International Workshop on Spoken Language Translation, 27-28 November 2006, Kyoto, Japan.

Full text available as:

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
322Kb

Abstract

In this paper, we give a description of the machine translation system developed at DCU that was used for our first participation in the evaluation campaign of the International Workshop on Spoken Language Translation (2006). This system combines two types of approaches. First, we use an EBMT approach to collect aligned chunks based on two steps: deterministic chunking of both sides and chunk alignment. We use several chunking and alignment strategies. We also extract SMT-style aligned phrases, and the two types of resources are combined. We participated in the Open Data Track for the following translation directions: Arabic-English and Italian-English, for which we translated both the single-best ASR hypotheses and the text input. We report the results of the system for the provided evaluation sets.

Item Type:Conference or Workshop Item (Paper)
Event Type:Workshop
Refereed:Yes
Subjects:Computer Science > Machine translating
DCU Faculties and Centres:Research Initiatives and Centres > National Centre for Language Technology (NCLT)
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Official URL:http://mastarpj.nict.go.jp/IWSLT2006/
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:Science Foundation Ireland, SFI OS/IN/1732
ID Code:15287
Deposited On:11 Mar 2010 14:24 by DORAS Administrator. Last Modified 28 Apr 2010 10:02

Download statistics

Archive Staff Only: edit this record